… Finally, we identify the promising paths to meet the reliability levels of … Spatial support
vector regression to detect silent errors in the exascale era. In Proceedings of the 16th IEEE/ACM …

… soft errors are linked to several temporal and spatial features, … As we progressing towards
exascale, applications are going to … resilience in GPUs and demonstrate that the ratio of silent …

… that exascale systems will experience faults and errors more fre… However, silent data corruption
(SDC) might require more … a global memory address space partitioned across the nodes. …

… ESCAPE strategy: (i) identify domain-specific key algorithmic … the optimisations, whereas
the error measures verify to what … most efficiently in grid point space, while horizontal gradients…

… are designed/utilized towards exascale computing, inevitably … on one-day period (27-March-2017)
due to space limit and … using partial labels based on PU learning and Support Vector …

… be more susceptible to soft errors ,eg silent data corruptions, … is able to detect errors online
soon after the error occurs so … for timely detection, faster recovery and less space overhead …

… different ML algorithms (eg, support vector machines, k-Nearest … To inject faults and check
for errors, this work introduces … investigations during early design space explorations process, …

… silent data corruption detectors by leveraging support vector … The right replication level to
detect and correct silent errors at … their spatial locality and providing the mean relative error (…

… scientists with expertise in exascale computing to discuss novel … for detection, containment
and mitigation of silent data … -resolution in space or time and the error estimators themselves …

… As we near exascale, resilience remains a major technical … spatial and temporal correlation
of memory errors to identify … RIPPER and the support vector machine perform reasonably well …